cc-metric-collector/sinks/sinkManager.go
Thomas Gruber 7840de7b82
Merge develop branch into main (#123)
* Add cpu_used (all-cpu_idle) to CpustatCollector

* Update cc-metric-collector.init

* Allow selection of timestamp precision in HttpSink

* Add comment about precision requirement for cc-metric-store

* Fix for API changes in gofish@v0.15.0

* Update requirements to latest version

* Read sensors through redfish

* Update golang toolchain to 1.21

* Remove stray error check

* Update main config in configuration.md

* Update Release action to use golang 1.22 stable release, no golang RPMs anymore

* Update runonce action to use golang 1.22 stable release, no golang RPMs anymore

* Update README.md

Use right JSON type in configuration

* Update sink's README

* Test whether ipmitool or ipmi-sensors can be executed without errors

* Little fixes to the prometheus sink (#115)

* Add uint64 to float64 cast option

* Add prometheus sink to the list of available sinks

* Add aggregated counters by gpu for nvlink errors

---------

Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>

* Ccmessage migration (#119)

* Add cpu_used (all-cpu_idle) to CpustatCollector

* Update cc-metric-collector.init

* Allow selection of timestamp precision in HttpSink

* Add comment about precision requirement for cc-metric-store

* Fix for API changes in gofish@v0.15.0

* Update requirements to latest version

* Read sensors through redfish

* Update golang toolchain to 1.21

* Remove stray error check

* Update main config in configuration.md

* Update Release action to use golang 1.22 stable release, no golang RPMs anymore

* Update runonce action to use golang 1.22 stable release, no golang RPMs anymore

* Switch to CCMessage for all files.

---------

Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>

* Switch to ccmessage also for latest additions in nvidiaMetric

* New Message processor (#118)

* Add cpu_used (all-cpu_idle) to CpustatCollector

* Update cc-metric-collector.init

* Allow selection of timestamp precision in HttpSink

* Add comment about precision requirement for cc-metric-store

* Fix for API changes in gofish@v0.15.0

* Update requirements to latest version

* Read sensors through redfish

* Update golang toolchain to 1.21

* Remove stray error check

* Update main config in configuration.md

* Update Release action to use golang 1.22 stable release, no golang RPMs anymore

* Update runonce action to use golang 1.22 stable release, no golang RPMs anymore

* New message processor to check whether a message should be dropped or manipulate it in flight

* Create a copy of message before manipulation

---------

Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>

* Update collector's Makefile and go.mod/sum files

* Use message processor in router, all sinks and all receivers

* Add support for credential file (NKEY) to NATS sink and receiver

* Fix JSON keys in message processor configuration

* Update docs for message processor, router and the default router config file

* Add link to expr syntax and fix regex matching docs

* Update sample collectors

* Minor style change in collector manager

* Some helpers for ccTopology

* LIKWID collector: write log owner change only once

* Fix for metrics without units and reduce debugging messages for messageProcessor

* Use shorted hostname for hostname added by router

* Define default port for NATS

* CPUstat collector: only add unit for applicable metrics

* Add precision option to all sinks using Influx's encoder

* Add message processor to all sink documentation

* Add units to documentation of cpustat collector

---------

Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
Co-authored-by: oscarminus <me@oscarminus.de>
Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
2024-12-19 23:00:14 +01:00

186 lines
4.6 KiB
Go

package sinks
import (
"encoding/json"
"fmt"
"os"
"sync"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
)
const SINK_MAX_FORWARD = 50
// Map of all available sinks
var AvailableSinks = map[string]func(name string, config json.RawMessage) (Sink, error){
"ganglia": NewGangliaSink,
"libganglia": NewLibgangliaSink,
"stdout": NewStdoutSink,
"nats": NewNatsSink,
"influxdb": NewInfluxSink,
"influxasync": NewInfluxAsyncSink,
"http": NewHttpSink,
"prometheus": NewPrometheusSink,
}
// Metric collector manager data structure
type sinkManager struct {
input chan lp.CCMessage // input channel
done chan bool // channel to finish / stop metric sink manager
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
sinks map[string]Sink // Mapping sink name to sink
maxForward int // number of metrics to write maximally in one iteration
}
// Sink manager access functions
type SinkManager interface {
Init(wg *sync.WaitGroup, sinkConfigFile string) error
AddInput(input chan lp.CCMessage)
AddOutput(name string, config json.RawMessage) error
Start()
Close()
}
// Init initializes the sink manager by:
// * Reading its configuration file
// * Adding the configured sinks and providing them with the corresponding config
func (sm *sinkManager) Init(wg *sync.WaitGroup, sinkConfigFile string) error {
sm.input = nil
sm.done = make(chan bool)
sm.wg = wg
sm.sinks = make(map[string]Sink, 0)
sm.maxForward = SINK_MAX_FORWARD
if len(sinkConfigFile) == 0 {
return nil
}
// Read sink config file
configFile, err := os.Open(sinkConfigFile)
if err != nil {
cclog.ComponentError("SinkManager", err.Error())
return err
}
defer configFile.Close()
// Parse config
jsonParser := json.NewDecoder(configFile)
var rawConfigs map[string]json.RawMessage
err = jsonParser.Decode(&rawConfigs)
if err != nil {
cclog.ComponentError("SinkManager", err.Error())
return err
}
// Start sinks
for name, raw := range rawConfigs {
err = sm.AddOutput(name, raw)
if err != nil {
cclog.ComponentError("SinkManager", err)
continue
}
}
// Check that at least one sink is running
if !(len(sm.sinks) > 0) {
cclog.ComponentError("SinkManager", "Found no usable sinks")
return fmt.Errorf("found no usable sinks")
}
return nil
}
// Start starts the sink managers background task, which
// distributes received metrics to the sinks
func (sm *sinkManager) Start() {
sm.wg.Add(1)
go func() {
defer sm.wg.Done()
// Sink manager is done
done := func() {
for _, s := range sm.sinks {
s.Close()
}
close(sm.done)
cclog.ComponentDebug("SinkManager", "DONE")
}
toTheSinks := func(p lp.CCMessage) {
// Send received metric to all outputs
cclog.ComponentDebug("SinkManager", "WRITE", p)
for _, s := range sm.sinks {
if err := s.Write(p); err != nil {
cclog.ComponentError("SinkManager", "WRITE", s.Name(), "write failed:", err.Error())
}
}
}
for {
select {
case <-sm.done:
done()
return
case p := <-sm.input:
toTheSinks(p)
for i := 0; len(sm.input) > 0 && i < sm.maxForward; i++ {
p := <-sm.input
toTheSinks(p)
}
}
}
}()
// Sink manager is started
cclog.ComponentDebug("SinkManager", "STARTED")
}
// AddInput adds the input channel to the sink manager
func (sm *sinkManager) AddInput(input chan lp.CCMessage) {
sm.input = input
}
func (sm *sinkManager) AddOutput(name string, rawConfig json.RawMessage) error {
var err error
var sinkConfig defaultSinkConfig
if len(rawConfig) > 0 {
err := json.Unmarshal(rawConfig, &sinkConfig)
if err != nil {
return err
}
}
if _, found := AvailableSinks[sinkConfig.Type]; !found {
cclog.ComponentError("SinkManager", "SKIP", name, "unknown sink:", sinkConfig.Type)
return err
}
s, err := AvailableSinks[sinkConfig.Type](name, rawConfig)
if err != nil {
cclog.ComponentError("SinkManager", "SKIP", name, "initialization failed:", err.Error())
return err
}
sm.sinks[name] = s
cclog.ComponentDebug("SinkManager", "ADD SINK", s.Name(), "with name", fmt.Sprintf("'%s'", name))
return nil
}
// Close finishes / stops the sink manager
func (sm *sinkManager) Close() {
cclog.ComponentDebug("SinkManager", "CLOSE")
sm.done <- true
// wait for close of channel sm.done
<-sm.done
}
// New creates a new initialized sink manager
func New(wg *sync.WaitGroup, sinkConfigFile string) (SinkManager, error) {
sm := new(sinkManager)
err := sm.Init(wg, sinkConfigFile)
if err != nil {
return nil, err
}
return sm, err
}